STA 220 - Final Project Data Analaysis

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Cmd+Shift+Enter.

# packages required
# install.packages("gridExtra")
#packages = c("gtrendsR","tidyverse","usmap")
#install.packages("mapproj")
# importing libraries
library(dplyr)
library(tidyverse)
library(data.table)
library(ggplot2)  
library(scales)
library(gridExtra)

# read in NYtimes Covid data tables 

# Cumulative Daily Cases and Deaths by 
# 1 - County Level
cty_data <-read.csv("us-counties.csv") 

# 2 - State Level
state_data <-read.csv("us-states.csv")
state_pop <-read.csv("state_pop.csv")

# 3 - 
us_data <-read.csv("us.csv")

# transforming date column from CHARACTER to DATE class
cty_data$date <- as.Date(cty_data$date)
state_data$date <- as.Date(state_data$date,format="%Y-%m-%d")
us_data$date <- as.Date(us_data$date)

# filter out dates before March 1st, 2020
cty_data <- base::subset(cty_data,date>"2020-02-29")
state_data <- base::subset(state_data,date>"2020-02-29")
us_data <- base::subset(us_data,date>"2020-02-29")

# Examination of US-wide Temporal Trends

# Use `filter()` to add a column named `new_cases` and 'new_deaths'
us_data$new_cases = as.numeric(stats::filter(us_data$cases,filter=c(1,-1), sides=1))

us_data$new_deaths = as.numeric(stats::filter(us_data$deaths,filter=c(1,-1), sides=1))
 
# Change first entry fo new deaths and new cases from NA to 0
us_data$new_cases[1]<-0
us_data$new_deaths[1]<-0

# Add Data on Season
season <- c("Spring","Summer","Winter","Fall")

# create df for seasons
season_df = data.frame(c(1:12),c("Winter","Winter","Spring","Spring","Spring","Summer","Summer","Summer","Fall","Fall","Fall","Winter"))
names(season_df)[1] <- "month"
names(season_df)[2] <- "season"

for (i in 1:length(us_data$date))
{
  if (month(us_data$date[i]) >= 3 & month(us_data$date[i]) < 6) {
    us_data$season[i] = season[1]
  } else if (month(us_data$date[i]) >= 6 & month(us_data$date[i]) < 9) {
    us_data$season[i] = season[2]
  } else if (month(us_data$date[i]) >= 9 & month(us_data$date[i]) < 12) {
    us_data$season[i] = season[3]
  } else {
    us_data$season[i] = season[4]
  }
}
us_data$season = as.factor(us_data$season)

## Plotting Below

# Timeseries of Covid Cases and Deaths through time
# Value used to transform the data
p1 <- ggplot(us_data, aes(x = date, y = new_cases)) +
            geom_line(color = "darkred") +
  labs(title="US Covid-19 Cases and Deaths",  y="Daily New Cases", x="")
  

p2 <- ggplot(us_data, aes(x = date, y = new_deaths)) +
            geom_line(color = "black") +
  labs(  y="Daily New Deaths", x="Date")
  
grid.arrange(p1,p2,nrow=2)

# scatter plot comparison of Cases Vs Deaths
gg <- ggplot(us_data,aes(x = new_cases, y = new_deaths, colour = season)) +
  geom_point() +
   labs(title="Cases Vs Deaths",subtitle="US Country-wide Covid Counts",y="Daily Deaths", x="Daily Cases")

plot(gg)

regions <- state.region
demographics <- state.x77
demographics = data.frame(demographics)
states_info <- data.frame("Name" = states_vect,"Region" = regions,"Pop"=demographics$Population)

options

function (...) 
.Internal(options(...))
<bytecode: 0x7ff0e39b9a78>
<environment: namespace:base>

#par(mfrow=c(2,1))
for (val in states_vect)
{
  # subset by state
  dum <- subset(state_data3, state == val)
  
    if (val == "Alabama"){
  plot(dum$date,dum$pc_new_cases,"l",  xlab="Date", ylab="Dly Per Capita Cases",ylim=c(0,0.25e-2),cex=3/4)
  par(new = TRUE)
  plot(dum$date,dum$pc_new_deaths,"l",  xlab="", ylab="",axes = FALSE,col=rgb(red = 1, green = 0, blue = 0, alpha = 0.5),ylim=c(0,0.1e-3))
  axis(side=4, col.axis = "dark red",col.ticks = "dark red", ylim=c(0,0.1e-3))
  mtext("Daily \n Per Capita Deaths",side=4,line=3, col = "dark red",cex=2/3)
  title(val)
  }else{
    
  plot(dum$date,dum$pc_new_cases,"l",  xlab="", ylab="",ylim=c(0,0.25e-2))
  par(new = TRUE)
  plot(dum$date,dum$pc_new_deaths,"l",  xlab="", ylab="",axes = FALSE,col=rgb(red = 1, green = 0, blue = 0, alpha = 0.5), ylim=c(0,0.1e-3))
  axis(side=4, col.axis = "dark red",col.ticks = "dark red")
  title(val)}
}

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Cmd+Option+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Cmd+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.